© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29087
    Prev
    Next
    INDEX
    Explanations

    resistance and loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪł
    -0.07
    opi
    -0.07
     Conte
    -0.07
    èµĭäºĪ
    -0.07
     Conf
    -0.07
    oggle
    -0.07
    OAD
    -0.07
    æ¶īå¤ĸ
    -0.06
    鸦çīĩ
    -0.06
    æľºåħ³
    -0.06
    POSITIVE LOGITS
    æįŁèĢĹ
    0.09
     losses
    0.08
    ilage
    0.08
    åĮħæīİ
    0.08
    éĺ»
    0.08
    ä¸Ģè·¯
    0.07
    çĸ²
    0.07
     ngh
    0.07
    èį·
    0.07
    缴éĢļ
    0.07
    Activations Density 0.012%

    No Known Activations